Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304098652> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4304098652 abstract "Video dehazing using deep-learning based methods has just received increasing attention in recent years. However, most existing methods tackle temporal consistency in the color domain only, which are less sensitive to small and imperceptible motions in a video, due to fog's drift and diffusion. In this work, we investigate in the frequency domain, which enables us to capture small motions effectively, and find that the phase component contains more semantic structures yet less haze information than the amplitude component of the hazy image. Based on these observations, we propose a novel phase-based memory network (PM-Net) to integrate the phase and color memory information for boosting video dehazing. Apart from the color memory from consecutive video frames, our PM-Net constructs a phase memory, which stores phase features of past video frames, and devise a cross-modal memory read (CMR) module, which fully leverages features from the color memory and the phase memory to boost features extracted from the current video frame for dehazing. Experimental results on the benchmark dataset of real hazy videos and a newly collected dataset of synthetic videos, show that the proposed PM-Net clearly outperforms the state-of-the-art image and video dehazing methods. Code is available at https://github.com/liuye123321/PM-Net." @default.
- W4304098652 created "2022-10-10" @default.
- W4304098652 creator A5000209938 @default.
- W4304098652 creator A5010970485 @default.
- W4304098652 creator A5016081925 @default.
- W4304098652 creator A5018742393 @default.
- W4304098652 creator A5031202827 @default.
- W4304098652 date "2022-10-10" @default.
- W4304098652 modified "2023-10-16" @default.
- W4304098652 title "Phase-based Memory Network for Video Dehazing" @default.
- W4304098652 cites W1905052409 @default.
- W4304098652 cites W1990370049 @default.
- W4304098652 cites W2003709967 @default.
- W4304098652 cites W2016598597 @default.
- W4304098652 cites W2017416107 @default.
- W4304098652 cites W2085744236 @default.
- W4304098652 cites W2107589634 @default.
- W4304098652 cites W2128254161 @default.
- W4304098652 cites W2133665775 @default.
- W4304098652 cites W2256362396 @default.
- W4304098652 cites W2519481857 @default.
- W4304098652 cites W2595967805 @default.
- W4304098652 cites W2777170053 @default.
- W4304098652 cites W2866634454 @default.
- W4304098652 cites W2895176907 @default.
- W4304098652 cites W2962754725 @default.
- W4304098652 cites W2963085671 @default.
- W4304098652 cites W2963306157 @default.
- W4304098652 cites W2985030998 @default.
- W4304098652 cites W2998249728 @default.
- W4304098652 cites W3034278302 @default.
- W4304098652 cites W3034331889 @default.
- W4304098652 cites W3035631962 @default.
- W4304098652 cites W3066471605 @default.
- W4304098652 cites W3083885798 @default.
- W4304098652 cites W3089141666 @default.
- W4304098652 cites W3094797876 @default.
- W4304098652 cites W3103309903 @default.
- W4304098652 cites W3174849075 @default.
- W4304098652 cites W3206886340 @default.
- W4304098652 doi "https://doi.org/10.1145/3503161.3547998" @default.
- W4304098652 hasPublicationYear "2022" @default.
- W4304098652 type Work @default.
- W4304098652 citedByCount "3" @default.
- W4304098652 countsByYear W43040986522023 @default.
- W4304098652 crossrefType "proceedings-article" @default.
- W4304098652 hasAuthorship W4304098652A5000209938 @default.
- W4304098652 hasAuthorship W4304098652A5010970485 @default.
- W4304098652 hasAuthorship W4304098652A5016081925 @default.
- W4304098652 hasAuthorship W4304098652A5018742393 @default.
- W4304098652 hasAuthorship W4304098652A5031202827 @default.
- W4304098652 hasConcept C126042441 @default.
- W4304098652 hasConcept C13280743 @default.
- W4304098652 hasConcept C154945302 @default.
- W4304098652 hasConcept C185798385 @default.
- W4304098652 hasConcept C205649164 @default.
- W4304098652 hasConcept C31972630 @default.
- W4304098652 hasConcept C41008148 @default.
- W4304098652 hasConcept C46686674 @default.
- W4304098652 hasConcept C65483669 @default.
- W4304098652 hasConcept C76155785 @default.
- W4304098652 hasConceptScore W4304098652C126042441 @default.
- W4304098652 hasConceptScore W4304098652C13280743 @default.
- W4304098652 hasConceptScore W4304098652C154945302 @default.
- W4304098652 hasConceptScore W4304098652C185798385 @default.
- W4304098652 hasConceptScore W4304098652C205649164 @default.
- W4304098652 hasConceptScore W4304098652C31972630 @default.
- W4304098652 hasConceptScore W4304098652C41008148 @default.
- W4304098652 hasConceptScore W4304098652C46686674 @default.
- W4304098652 hasConceptScore W4304098652C65483669 @default.
- W4304098652 hasConceptScore W4304098652C76155785 @default.
- W4304098652 hasLocation W43040986521 @default.
- W4304098652 hasOpenAccess W4304098652 @default.
- W4304098652 hasPrimaryLocation W43040986521 @default.
- W4304098652 hasRelatedWork W1967456564 @default.
- W4304098652 hasRelatedWork W2004195487 @default.
- W4304098652 hasRelatedWork W2068162367 @default.
- W4304098652 hasRelatedWork W2080322084 @default.
- W4304098652 hasRelatedWork W2348820921 @default.
- W4304098652 hasRelatedWork W2415044327 @default.
- W4304098652 hasRelatedWork W2574246024 @default.
- W4304098652 hasRelatedWork W2789578481 @default.
- W4304098652 hasRelatedWork W2921853716 @default.
- W4304098652 hasRelatedWork W4312095940 @default.
- W4304098652 isParatext "false" @default.
- W4304098652 isRetracted "false" @default.
- W4304098652 workType "article" @default.